update readme for vctk hifigan, test=tts

docs/source/released_model.md

@@ -55,6 +55,7 @@ Parallel WaveGAN| VCTK |[PWGAN-vctk](https://github.com/PaddlePaddle/PaddleSpeec
 Style MelGAN | CSMSC |[Style MelGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc4)|[style_melgan_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/style_melgan/style_melgan_csmsc_ckpt_0.1.1.zip)| | |
 HiFiGAN | CSMSC |[HiFiGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc5)|[hifigan_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_ckpt_0.1.1.zip)|[hifigan_csmsc_static_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_static_0.1.1.zip)|50MB|
 HiFiGAN | AISHELL-3 |[HiFiGAN-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc5)|[hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip)|||
+HiFiGAN | VCTK |[HiFiGAN-vctk](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/vctk/voc5)|[hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip)|||
 WaveRNN | CSMSC |[WaveRNN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc6)|[wavernn_csmsc_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/wavernn/wavernn_csmsc_ckpt_0.2.0.zip)|[wavernn_csmsc_static_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/wavernn/wavernn_csmsc_static_0.2.0.zip)|18MB|
 
 

examples/vctk/tts3/local/synthesize_e2e.sh

@@ -49,4 +49,4 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
         --speaker_dict=dump/speaker_id_map.txt \
         --spk_id=0 \
         --inference_dir=${train_output_path}/inference
-fi
+fi

examples/vctk/voc5/README.md

@@ -133,7 +133,21 @@ optional arguments:
 5. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.
 
 ## Pretrained Model
+The pretrained model can be downloaded here [hifigan_vctk_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_vctk_ckpt_0.2.0.zip).
 
 
+Model | Step | eval/generator_loss | eval/mel_loss| eval/feature_matching_loss
+:-------------:| :------------:| :-----: | :-----: | :--------:
+default| 1(gpu) x 2500000|58.092|0.1234|24.384
+
+HiFiGAN checkpoint contains files listed below.
+
+```text
+hifigan_vctk_ckpt_0.2.0
+├── default.yaml                  # default config used to train hifigan
+├── feats_stats.npy               # statistics used to normalize spectrogram when training hifigan
+└── snapshot_iter_2500000.pdz     # generator parameters of hifigan
+```
+
 ## Acknowledgement
 We adapted some code from https://github.com/kan-bayashi/ParallelWaveGAN.

paddlespeech/cli/tts/infer.py

@@ -237,6 +237,30 @@ pretrained_models = {
         'speech_stats':
         'feats_stats.npy',
     },
+    "hifigan_aishell3-zh": {
+        'url':
+        'https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip',
+        'md5':
+        '3bb49bc75032ed12f79c00c8cc79a09a',
+        'config':
+        'default.yaml',
+        'ckpt':
+        'snapshot_iter_2500000.pdz',
+        'speech_stats':
+        'feats_stats.npy',
+    },
+    "hifigan_vctk-en": {
+        'url':
+        'https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_vctk_ckpt_0.2.0.zip',
+        'md5':
+        '7da8f88359bca2457e705d924cf27bd4',
+        'config':
+        'default.yaml',
+        'ckpt':
+        'snapshot_iter_2500000.pdz',
+        'speech_stats':
+        'feats_stats.npy',
+    },
 
     # wavernn
     "wavernn_csmsc-zh": {
@@ -365,6 +389,8 @@ class TTSExecutor(BaseExecutor):
                 'mb_melgan_csmsc',
                 'style_melgan_csmsc',
                 'hifigan_csmsc',
+                'hifigan_aishell3',
+                'hifigan_vctk',
                 'wavernn_csmsc',
             ],
             help='Choose vocoder type of tts task.')

paddlespeech/t2s/exps/synthesize_e2e.py

@@ -63,7 +63,7 @@ def evaluate(args):
 
     output_dir = Path(args.output_dir)
     output_dir.mkdir(parents=True, exist_ok=True)
-    merge_sentences = True
+    merge_sentences = False
     # Avoid not stopping at the end of a sub sentence when tacotron2_ljspeech dygraph to static graph
     # but still not stopping in the end (NOTE by yuantian01 Feb 9 2022)
     if am_name == 'tacotron2':

tests/unit/cli/test_cli.sh

@@ -19,8 +19,10 @@ paddlespeech tts --voc mb_melgan_csmsc --input "你好，欢迎使用百度飞
 paddlespeech tts --voc style_melgan_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！"
 paddlespeech tts --voc hifigan_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！"
 paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0
+paddlespeech tts --am fastspeech2_aishell3 --voc hifigan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0
 paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "Life was like a box of chocolates, you never know what you're gonna get."
 paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "Life was like a box of chocolates, you never know what you're gonna get." --lang en --spk_id 0
+paddlespeech tts --am fastspeech2_vctk --voc hifigan_vctk --input "Life was like a box of chocolates, you never know what you're gonna get." --lang en --spk_id 0
 paddlespeech tts --am tacotron2_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！"
 paddlespeech tts --am tacotron2_csmsc --voc wavernn_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！"
 paddlespeech tts --am tacotron2_ljspeech --voc pwgan_ljspeech --lang en --input "Life was like a box of chocolates, you never know what you're gonna get."